Improving the Performance of Predictive Encoder by Changing the Image Content Arrangement Using Genetic Algorithm

Image compressiontechniquescan bedividedinto two categoriesoflossyandlossless. Predictiveencoder isthe basis of many losslessimagecompression methods. Thisencoder predictsthe valuesofimage pixelsusing theirneighboringpixelsvalues. The difference betweenthe actual valueand thepredictedvalue of each pixelis consideredthe errorandthese error valuesarecoded.In this paper, a pre-processingmethodis proposed tochangethe image content arrangementsothatthe correlations between the neighboring pixelsincrease.By increasing the correlation between neighboring pixels, predictive encoder can more accurately predict the value of each pixel, as a result, entropy is reduced in the error image. According toinformation theory, thelower the imageentropy leads to the higher the capability of theentropy encoderinitscompression.In the proposed method,using the genetic algorithm, an appropriate geometrictransformationof rotationandreflectionis appliedoneach blockofthe image to strengthen the correlation between neighboring pixels.Inthispaper, twocompression methods,losslessJPEG andCALIC that are based on predictivecodingareevaluated.The evaluation results ofthe proposed methodonmultiple imagesshow thattheproposedpre-processingmethodimprovesthecompressionrate of these two methods.